Read original ↗
paperarXivTrust 82 · PrimaryPublished 1mo agoLive · 1mo ago

Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration

Existing autonomous research agents can support parts of the research process, but most systems still treat research as either an isolated assistant task or a closed workflow. Therefore, autonomous science needs a collaboration infrastructure that coordinates projects, agents, and digital and physical resources. We identify this as a shift from code-centered execution loops to research-oriented collaboration processes, where questions, evidence, participants, and resources must be coordinated under uncertainty. In this framing, an agent may be an AI system, a human researcher, a team, a labora

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

Covers

Covers (incoming)

Implements (incoming)

Related across the graph

repoastronomer/agentsrepoopenonion/connectonionrepoduckbugio/flockrepostarpig1129/DATAGENnewsLearning to lead in a hybrid human-AI enterpriserepojonwiggins/optiorepoTHU-Team-Eureka/EurekAgentrepoapache/texerarepoweb3dev1337/agent-workspacerepoStarlight143/cruciblenewsOpen-source agent framework crosses 50k starsnewsAnthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines - MarkTechPostrepoFabiojvv/ai-cortex-hubrepoTeam-Commonly/commonlyrepoTauricResearch/TradingAgentsrepodrpedapati/sciclawnewsAn agentic artificially intelligent X-ray scientistnewsNVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Sciencerepojahwag/clemnewsGoogle DeepMind is worried about what happens when millions of agents start to interactrepospring-projects/spring-ainewsGoogle's Agentic Peer-Reviewer Handled ~10K Papers at ICML/STOC — Formal Research Paper Now Out [R]newsAgentic AI for Robot TeamsrepojnMetaCode/agency-agents-zhrepodatawhalechina/hello-agentsnewsAnthropic wants to develop its own drugsrepowecode-ai/WegentrepoUnity-Technologies/ml-agentsnewsAI agents are not your “coworkers”repowanshuiyin/Auto-claude-code-research-in-sleepnewsCo-Scientist: A multi-agent AI partner to accelerate researchrepoNirDiamant/GenAI_Agentsrepoworldbench/awesome-ai-auto-researchnewsAnthropic’s Claude Science bets on workflow, not a new model, to win over scientistsrepoLabNow-ai/lab-foundationrepoInternScience/ResearchClawBenchnewsMicrosoft Discovery Runs Agentic Science Workflows - Let's Data Sciencerepogoogle-research/google-research

Topics